xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-19 04:27:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

[V1][Sampler] Don't apply temp for greedy-only (#13311)

Browse Source 
Signed-off-by: Nick Hill <nhill@redhat.com>
This commit is contained in:
Nick Hill 2025-02-14 18:10:53 -08:00 committed by GitHub
parent e7eea5a520
commit 6a854c7a2b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
vllm/v1/sample/sampler.py
View File

@ -41,8 +41,6 @@ class Sampler(nn.Module):
logits = self.apply_logits_bias(logits, sampling_metadata)
# Apply penalties (e.g., min_tokens, freq_penalties).
logits = self.apply_penalties(logits, sampling_metadata)
# Apply temperature.
logits = self.apply_temperature(logits, sampling_metadata.temperature)
# Sample the next token.
sampled = self.sample(logits, sampling_metadata)
@ -82,9 +80,21 @@ class Sampler(nn.Module):
) -> torch.Tensor:
assert not (sampling_metadata.all_greedy
and sampling_metadata.all_random)
if sampling_metadata.all_greedy:
return self.greedy_sample(logits)
if sampling_metadata.all_random:
greedy_sampled = None
else:
greedy_sampled = self.greedy_sample(logits)
if sampling_metadata.all_greedy:
return greedy_sampled
# Apply temperature.
logits = self.apply_temperature(logits, sampling_metadata.temperature)
# Apply min_p.
if not sampling_metadata.no_min_p:
logits = self.apply_min_p(logits, sampling_metadata.min_p)
# Apply top_k and/or top_p.
random_sampled = self.topk_topp_sampler(
logits,
sampling_metadata.generators,
@ -94,13 +104,9 @@ class Sampler(nn.Module):
sampling_metadata.top_p,
)
if not sampling_metadata.no_min_p:
logits = self.apply_min_p(logits, sampling_metadata.min_p)
if sampling_metadata.all_random:
if greedy_sampled is None:
return random_sampled
greedy_sampled = self.greedy_sample(logits)
sampled = torch.where(
sampling_metadata.temperature < _SAMPLING_EPS,
greedy_sampled,